Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kamranjon
58 days ago
|
parent
|
context
|
favorite
| on:
DeepSeek V4 Flash 0731 Intelligence, Performance a...
Generally get 20-25tps - prefill is pretty good around 400-450tps. I have been using compaction at around 100k tokens but mostly just cause it was the default in pi coding agent - might see if i can expand it a bit.
Lwerewolf
58 days ago
[–]
I've had it run to ~400k when debugging "obscure" (to it) sequences. Wouldn't recommend more.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: